- My Forums
- Tiger Rant
- LSU Recruiting
- SEC Rant
- Saints Talk
- Pelicans Talk
- More Sports Board
- Fantasy Sports
- Golf Board
- Soccer Board
- O-T Lounge
- Tech Board
- Home/Garden Board
- Outdoor Board
- Health/Fitness Board
- Movie/TV Board
- Book Board
- Music Board
- Political Talk
- Money Talk
- Fark Board
- Gaming Board
- Travel Board
- Food/Drink Board
- Ticket Exchange
- TD Help Board
Customize My Forums- View All Forums
- Show Left Links
- Topic Sort Options
- Trending Topics
- Recent Topics
- Active Topics
Started By
Message
re: .
Posted on 11/11/16 at 1:34 pm to buckeye_vol
Posted on 11/11/16 at 1:34 pm to buckeye_vol
quote:
Well maybe it's just a big fish small pond phenomenon on that field, but he was again the best polling forecaster by a large margin.
He shite the bed.
0
Posted on 11/11/16 at 1:34 pm to buckeye_vol
quote:
And you can criticize the methodology
That's what you don't understand. It isn't a methodology. He's an aggregator. You are acting like he created anything. He uses polls as predictors. That's it. He didn't create doing that. He went against people who use that data with other data.
He isn't a predictor, he's an aggregator.This post was edited on 11/11/16 at 1:36 pm
Posted on 11/11/16 at 1:34 pm to DelU249
LSU came within 11 points of beating Bama in TS.
Posted on 11/11/16 at 1:35 pm to tagatose
quote:
Dude has lost ALL credibility.
...and that's after he destroyed his credibility in the Democrat Party's primaries.
This guy is a fortune teller with a spread sheet. He failed, and failed over and over again.
This post was edited on 11/11/16 at 1:36 pm
Posted on 11/11/16 at 1:39 pm to buckeye_vol
It's not noteworthy that he almost won a state that hasn't been red since the 70s? They were the only state that voted for Mondale for Christ's sake...
This post was edited on 11/11/16 at 1:41 pm
Posted on 11/11/16 at 1:48 pm to buckeye_vol
The key takeaway here is that Nate Silver is a joke. He was a joke in the primaries. He was a joke in the World Series. He was a MASSIVE FAILURE in the general election.
Posted on 11/11/16 at 2:03 pm to member12
quote:Huh? 538 had the Cubs with a 2/3 to 3/4 chance of winning. After getting down 3-1, obviously they had far worse odds (as they should). So how was that a joke?
He was a joke in the World Series.
Posted on 11/11/16 at 2:08 pm to Jake88
I'm going to add holy diver to my trump playlist
Posted on 11/11/16 at 2:47 pm to Catman88
quote:It's noteworthy, and it's part of the narrative of Trump flipping the midwestern states. It's just not a individual story in and of itself as a single state.
It's not noteworthy that he almost won a state that hasn't been red since the 70s? They were the only state that voted for Mondale for Christ's sake...
But as it relates to the impact of the outcome, the fact that 4 states, representing 75 electoral votes, were within 1.3% of changing the election.
In other words, there was altogether a 227,000 vote (the population of Baton Rouge) difference in those four states. Just flipping those votes would only change the popular vote by 0.36% but it would change the EC vote by 27.88%, or 77 times more impactful on the EC than the popular vote.
I like the electoral college (although I wish states had some allocation based on proportion or district like ME and NE); however, that is a very interesting dynamic.
I mean there has only been 4 out of 58 presidential elections with a popular vote-EC split. And the only other one in recent times had a much closer split. It's an interesting story.
Posted on 11/11/16 at 2:49 pm to buckeye_vol
quote:your response to him brings up something I find very odd about the prob/stat junkies on this board
Sure. It's also true that wealth in not normally disrupted so it should be modeled on something like a Pareto Distribution, plus using a far larger sample than N = 2.
RCP...why the frick is an average something people point to with any kind of credibility.
Posted on 11/11/16 at 2:51 pm to buckeye_vol
quote:if you're saying long term then yes it is a narrative but it's a real possibility of a shift in those states
and it's part of the narrative of Trump flipping the midwestern states
i'm just going to give you the benefit of the doubt here because if you would even use the word "narrative" to describe him winning/flipping those states...holy bejesus
Posted on 11/11/16 at 2:52 pm to DelU249
After the past year, Nate Silver has become about as credible or useful as CNN or the National Inquirer.
Posted on 11/11/16 at 2:57 pm to dewster
It's hard to argue against that, because his defenders say
2012: he nailed it. Every state, percentages, etc.
2016: he may have been horribly wrong but he was the least wrong which makes him the best
2012: he nailed it. Every state, percentages, etc.
2016: he may have been horribly wrong but he was the least wrong which makes him the best
Posted on 11/11/16 at 3:17 pm to DelU249
quote:
2016: he may have been horribly wrong but he was the least wrong which makes him the best
2016: Hillary should be prez because she has the most votes right now
Posted on 11/11/16 at 3:23 pm to DelU249
quote:I said narrative because we were talking about news articles, which have a narrative (a story of the events that took place). What issue do you have with its usage?
i'm just going to give you the benefit of the doubt here because if you would even use the word "narrative" to describe him winning/flipping those states...holy bejesus
Posted on 11/11/16 at 3:32 pm to DelU249
quote:Well it's more reliable than picking and choosing one poll (obviously).
RCP...why the frick is an average something people point to with any kind of credibility.
But it's a quick and easy reference to the state of the polling as it compares to the outcome.
That said, it doesn't account for trends, and more importantly--and related--the time frame for the polls included in the average can vary greatly.
So it's not extremely accurate because of that (and some other reasons), and the trends are an important predictive component (which 538 uses).
So it's used for convenience to get a raw estimator.
This post was edited on 11/11/16 at 3:33 pm
Posted on 11/11/16 at 3:47 pm to buckeye_vol
quote:which often implies that it is fictitious
story
don't tell stories
I figured you weren't saying it was untrue but wanted to clarify
Posted on 11/11/16 at 3:49 pm to buckeye_vol
quote:but it's used as a defense of polling...the case is made on an individual basis IMO, but to mitigate how far off most polls were...all the reputable ones...defenders go to the average.
than picking and choosing one poll (obviously).
But it's a quick and easy reference to the state of the polling as it compares to the outcome.
That said, it doesn't account for trends, and more importantly--and related--the time frame for the polls included in the average can vary greatly.
So it's not extremely accurate because of that (and some other reasons), and the trends are an important predictive component (which 538 uses).
So it's used for convenience to get a raw estimator
Posted on 11/11/16 at 4:36 pm to DelU249
quote:Well each poll obviously has a margin of error, even if it's a perfectly representative sample. So aggregating the polls decreases that margin. In addition, since each poll probably polls from a slightly different population due to sampling methodology, this should hopefully decrease error due to sampling as well.
but it's used as a defense of polling...the case is made on an individual basis IMO, but to mitigate how far off most polls were...all the reputable ones...defenders go to the average.
Clearly though, because turnout is essentially unknown there is a risk the sampling will be disproportionately biased one or the way or the other. In 2012 it was biased towards Romney and on 2016 it was biased toward Clinton.
As usual it appears that R leaners are more consistent in their turnout (evidenced by midterms), whereas D leaners are more inconsistent.
Posted on 11/11/16 at 5:14 pm to DelU249
What if Trump had been two points higher? Did he do that analysis?
Page 4 of 5
Popular
Back to top
Follow TigerDroppings for LSU Football News